Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment. However, the substantial advancements in versatility and performance these models offer come at a significant cost in terms of hardware resources. To support the growth of these large models in a scalable and environmentally sustainable way, there has been a considerable focus on developing resource-efficient strategies. This survey delves into the critical importance of such research, examining both algorithmic and systemic aspects. It offers a comprehensive analysis and valuable insights gleaned from existing literature, encompassing a broad array of topics from cutting-edge model architectures and training/serving algorithms to practical system designs and implementations. The goal of this survey is to provide an overarching understanding of how current approaches are tackling the resource challenges posed by large foundation models and to potentially inspire future breakthroughs in this field.
@article{arxiv.2401.08092,
title = {A Survey of Resource-efficient LLM and Multimodal Foundation Models},
author = {Mengwei Xu and Wangsong Yin and Dongqi Cai and Rongjie Yi and Daliang Xu and Qipeng Wang and Bingyang Wu and Yihao Zhao and Chen Yang and Shihe Wang and Qiyang Zhang and Zhenyan Lu and Li Zhang and Shangguang Wang and Yuanchun Li and Yunxin Liu and Xin Jin and Xuanzhe Liu},
journal= {arXiv preprint arXiv:2401.08092},
year = {2024}
}